Skip to content

iesl/leopard

master
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 

Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks

This repository contains datasets used for evaluating few-shot performance introduced in the following paper. Please cite the paper if you use these datasets:

Paper

@inproceedings{bansal2020,
    title = "Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks",
    author = "Bansal, Trapit  and Jha, Rishikesh  and McCallum, Andrew",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics (COLING)",
    year = "2020",
}

Data

Data is available in two formats: JSON and tf_record
Data is organized into a folder for each task.
Each task contains 10 sampled datasets for training for each k-shot.
Training file for i-th sample and k-th shot is named task_train_i_k, and the test data is in file task_eval.

Code

Code and trained models for this work are published in the following repository: MetaNLP

Please refer to the ReadMe there for instructions on using the model.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published